Ancient Pompeii frescoes are to be assembled by an AI robot

RePAIR technology is made to solve intricate puzzles whose components may be broken, fading, scattered, or completely absent. Its artificial intelligence (A.I.) program might examine the numerous pieces of a centuries-old Roman vase and determine how they fit together. After that, a pair of robotic arms would put them back together, as per Artnet.

“We wanted to save the archaeologists precious time that they waste on assembling fragments, which sometimes takes years and sometimes never succeeds,” one of the RePair’s founding scientists, Ohad Ben-Shahar of Ben-Gurion University’s Department of Computer Science, told Haaretz.

Pompeii: The first target

One of the project’s initial goals is a pair of 2,000-year-old frescoes from Pompeii, an ancient Roman city that was destroyed by Mount Vesuvius’ eruption in 79 CE. The House of the Painters at Work in the Insula of the Chaste Lovers originally housed one fresco, and the Schola Armaturarum provided the other.

Like many other items discovered during the Pompeii site excavation, thousands of frescoes fragments were preserved in layers of volcanic ash. But, following investigation, specialists concluded that reassembling those fragments would be practically impossible for people to complete. As a result, for many years, the shards have been largely forgotten in a warehouse outside of Pompeii.

RePAIR will eventually be able to handle intricate tasks nearly entirely on its own, from scanning through assembly, if everything goes according to plan. The robot will assemble the vessel overnight, and when the archaeologist returns from the excavation site in the evening, they will be able to get the full vessel the next morning.

“The computer will present intermediate results to us as necessary and will ask to consult with a human expert who will determine whether the result is good or whether the computer will have to be adjusted to help put it in the right direction,” added Ben-Shahar. “People have always built machines to help them. In our project, autonomous machines will be helped by people.”